Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Far-field wireless charging receiving target detection method based on convolutional neural network

A convolutional neural network and wireless charging technology is applied in the field of computer vision to achieve high detection accuracy and improve efficiency

Pending Publication Date: 2019-04-16
TONGJI UNIV
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, traditional wireless charging solutions, such as magnetic resonance, magnetic induction, and microwave charging, face challenges in distance, power, safety, and mobility.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Far-field wireless charging receiving target detection method based on convolutional neural network
  • Far-field wireless charging receiving target detection method based on convolutional neural network
  • Far-field wireless charging receiving target detection method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0028] The receiving end of the far-field wireless charging system RBC can be a computer, a desk lamp or various IoT devices. It is a huge project to consider all kinds of receiving ends when training the neural network. The mobile phone is the most common and important charging object, so when implementing the scheme, the mobile phone is used as the representative of the RBC receiver, such as figure 2 Shown is the implementation process of the method of the present invention: 1) at first set up the mobile phone data set; 2) put the data set into the designed deep convolutional neural network for training, and obtain the deep convolutional network specially detecting the mobile phone target; 3) combine The trained network is embedded into the RBC control system; 4) Put the pictures captured by the camera into the network for analysis, and obtain the possible locations of several mobile phone targets; 5) Laser scan the pre-positioned positions to confirm the positioning results...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a far-field wireless charging receiving target detection method based on a convolutional neural network. According to the method, a camera is added to a far-field wireless charging transmitting end. The method is mainly characterized in that the deep convolutional neural network is used for target detection, only a camera is needed to acquire a picture, the accuracy dependson an algorithm, and equipment errors do not need to be worried about. By taking the detection time as an index, the network structure is optimized to improve the detection efficiency. The idea of animage pyramid is used, connection of different feature maps is considered, and the small target detection capability is improved. A MaskRCNN network framework and a ResNet101 backbone network are modified, and the detection accuracy and speed are considered. A method of visual prepositioning and then laser scanning fine positioning is adopted, and the traversal scanning positioning time is shortened to one third.

Description

technical field [0001] The present invention relates to the field of computer vision, in particular to a convolutional neural network-based target detection method for far-field wireless charging receivers. Background technique [0002] In recent years, the demand for power supply of electronic devices has been increasing, and the battery life has reached the bottleneck, so wireless charging has received more and more attention. However, traditional wireless charging solutions, such as magnetic resonance, magnetic induction, and microwave charging, face challenges in distance, power, safety, and mobility. Different from traditional charging solutions, RBC (Resonant Beam Charging) far-field wireless charging technology uses laser as the transmission medium, which can realize safe and mobile energy transmission with meter-level distance and watt-level power. [0003] Before the energy transmission link is established, the sending end of the RBC must know the location informat...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/10G06F18/2413
Inventor 吴敖洲刘庆文方稳张清清邓浩刘明清姜赛
Owner TONGJI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products